News Sources, Journalists and Climate Change
Sylvan Zheng
Basic Descriptives
Ns
nrow(articles)## [1] 13136nrow(sources)## [1] 77454nrow(authors)## [1] 1842Articles
Number Over Time By outlet
articles %>%
group_by(year, source) %>%
summarize(n = n()) %>%
ggplot(aes(x = year, y = n, color = source)) +
geom_line() +
theme_bw() +
scale_x_continuous(breaks = c(2012, 2014, 2016, 2018, 2020, 2022)) +
labs(
x = "Year",
y = "Number of Articles",
color = "Newspaper"
) +
theme_min
ggsave(here("paper/figures/time_trend_n_articles.png"), width = 6, height = 4)Sources
Number per Article
articles$n_srcs %>% hist()
summary(articles$n_srcs)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 4.000 6.000 5.896 8.000 31.000Number per Article over Time
sources %>%
group_by(year) %>%
summarize(n = n(), n_articles = length(unique(filename)), avg_sources = n / n_articles) %>%
ggplot(aes(x = year, y = avg_sources)) +
geom_line() +
scale_x_continuous(breaks = seq(2012, 2022, 2)) +
theme_min
etable(feols(n_srcs ~ post2016, data=articles)) %>% htmlTable| feols(n_srcs ~ p.. | ||
|---|---|---|
| 1 | Dependent Var.: | n_srcs |
| 2 | ||
| 3 | Constant | 5.272*** (0.0492) |
| 4 | post2016TRUE | 0.8374*** (0.0570) |
| 5 | _______________ | __________________ |
| 6 | S.E. type | IID |
| 7 | Observations | 13,136 |
| 8 | R2 | 0.01617 |
| 9 | Adj. R2 | 0.01610 |
Number per Outlet
sources %>%
group_by(source) %>%
summarize(n = n(), n_articles = length(unique(filename)), avg_sources = n / n_articles) %>%
kable()| source | n | n_articles | avg_sources |
|---|---|---|---|
| Chicago Tribune | 3052 | 578 | 5.280277 |
| Los Angeles Times | 10173 | 1796 | 5.664254 |
| New York Times | 28282 | 4671 | 6.054806 |
| USA Today | 3397 | 684 | 4.966374 |
| Wall Street Journal | 12081 | 2286 | 5.284777 |
| Washington Post | 20469 | 3121 | 6.558475 |
sources %>%
group_by(source, year) %>%
summarize(n = n(), n_articles = length(unique(filename)), avg_sources = n / n_articles) %>%
ggplot(aes(x = year, y = avg_sources, color = source)) +
geom_line() +
theme_min
# The example articles
# filter(str_detect(filename, "1270322870.xml|1731405273.xml")) %>%Source Types (Table 1)
gen.cats <- table(sources$category) %>%
prop.table() %>%
as.data.frame() %>%
rename(Category = "Var1") %>%
mutate(
Freq = paste0(round(100 * Freq, digits = 1), "%")
)
sources$category2 <- case_when(
sources$env_category == "environmental" ~ paste(sources$category, "- Environmental"),
sources$env_category == "fossil fuel" ~ paste(sources$category, "- Fossil Fuel"),
sources$category == "Politician" & sources$pol_party == "Democrat" ~ "Politician - Democrat",
sources$category == "Politician" & sources$pol_party == "Republican" ~ "Politician - Republican",
sources$category == "Politician" & sources$category == "Politician" ~ "Politician - International",
sources$category == "Citizen" ~ "Other",
sources$category == "Advocacy" ~ "Advocacy - Other",
sources$category == "Business" ~ "Business - Other",
TRUE ~ sources$category
)
sub.cats <- table(sources$category2) %>%
prop.table() %>%
as.data.frame() %>%
rename(Category = "Var1") %>%
mutate(
Freq = paste0(round(100 * Freq, digits = 1), "%")
)
rbind(gen.cats, sub.cats) %>% distinct() %>% kable()| Category | Freq |
|---|---|
| Academic | 10.2% |
| Advocacy | 21.5% |
| Bureaucrat | 12.4% |
| Business | 15% |
| International | 11.3% |
| Media | 5.6% |
| Other | 4.1% |
| Politician | 19.8% |
| Advocacy - Environmental | 13.7% |
| Advocacy - Fossil Fuel | 0.4% |
| Advocacy - Other | 7.5% |
| Business - Environmental | 2% |
| Business - Fossil Fuel | 4.3% |
| Business - Other | 8.6% |
| Politician - Democrat | 12% |
| Politician - International | 2.8% |
| Politician - Republican | 5% |
Distribution of source types by newspaper
sources %>%
mutate(
category = factor(category, levels = c(
"Academic",
"Advocacy",
"Business",
"Bureaucrat",
"Politician",
"International",
"Media",
"Other"
))
) %>%
group_by(category, source) %>%
summarize(n = n()) %>%
group_by(source) %>%
mutate(prop = n / sum(n)) %>%
ungroup() %>%
ggplot(
aes(x = reorder(source, n), fill = fct_rev(category), y = prop)
) +
geom_bar(stat = "identity") +
theme_bw() +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), legend.position = "bottom") +
labs(x = "", y = "Prop", fill = "Category") +
scale_fill_brewer(palette = "Set2", direction = -1) +
coord_flip() +
guides(fill = guide_legend(reverse = TRUE))
ggsave(here("paper/figures/source-dist.png"), width = 8, height = 6)
sources.s2 <- sources %>%
mutate(category.slant2 = case_when(
category.slant %in% c("Bureaucrat", "International", "Politician") ~ "Other",
category.slant %in% c("Academic", "Media", "Advocacy") ~ "Other",
TRUE ~ category.slant
)) %>%
mutate(
category.slant2 = factor(category.slant2, levels = c(
"Environmental",
"Business",
"Fossil Fuel",
"Democrat",
"Republican",
"Other"
))
)
sources.s2 %>%
group_by(category.slant2, source) %>%
summarize(n = n()) %>%
group_by(source) %>%
mutate(prop = n / sum(n)) %>%
ungroup() %>%
ggplot(
aes(x = reorder(source, n), fill = fct_rev(category.slant2), y = prop)
) +
geom_bar(stat = "identity") +
scale_fill_manual(values = c(
"Environmental" = "#91bfdb",
"Democrat" = "#4575b4",
"Republican" = "#d73027",
"Fossil Fuel" = "#fc8d59",
"Business" = "#fee090",
"Other" = "#ffffbf"
)) +
theme_bw() +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), legend.position = "bottom") +
labs(x = "", y = "Prop", fill = "Category") +
coord_flip() +
guides(fill = guide_legend(reverse = TRUE))
ggsave(here("paper/figures/source-dist-2.png"), width = 8, height = 6)
sources.s2$category.slant2 %>%
table() %>%
prop.table() %>%
kable| . | Freq |
|---|---|
| Environmental | 0.1536783 |
| Business | 0.0844501 |
| Fossil Fuel | 0.0465050 |
| Democrat | 0.1446923 |
| Republican | 0.0551811 |
| Other | 0.5154931 |
DIME correlates to category
feols(cfscore ~ category.slant, data = sources) %>%
etable %>%
htmlTable| . | ||
|---|---|---|
| 1 | Dependent Var.: | cfscore |
| 2 | ||
| 3 | Constant | 0.8953*** (0.0096) |
| 4 | category.slantAdvocacy | -0.9919*** (0.0152) |
| 5 | category.slantBusiness | -0.7901*** (0.0144) |
| 6 | category.slantDemocrat | -1.468*** (0.0117) |
| 7 | category.slantEnvironmental | -1.716*** (0.0130) |
| 8 | category.slantFossilFuel | -0.5482*** (0.0152) |
| 9 | category.slantInternational | -1.378*** (0.0856) |
| 10 | category.slantOther | -0.9430*** (0.0239) |
| 11 | ___________________________ | ___________________ |
| 12 | S.E. type | IID |
| 13 | Observations | 23,876 |
| 14 | R2 | 0.50244 |
| 15 | Adj. R2 | 0.50229 |
Top Source DIME scores
dt <- sources %>%
filter(cfscore_src != "politician") %>%
filter(!is.na(org_id)) %>%
group_by(org_id, cfscore.i2) %>%
summarize(
n = n(), cfscore = fmode(cfscore), name = first(organization_name), category.slant = first(category.slant)
) %>%
arrange(desc(n)) %>%
filter(!is.na(cfscore)) %>%
head(50) %>%
arrange(n) %>%
mutate(rn = 51 - row_number(), n_size = n + 10)
dt %>% ggplot(aes(x = cfscore, size = sqrt(n), y = n, color = cfscore)) +
theme_bw() +
scale_y_log10() +
scale_x_continuous(limits = c(-1.5, 1.2)) +
scale_color_gradient(low = "blue", high = "red") +
geom_vline(xintercept = 0, lty = "dashed") +
theme(panel.grid = element_blank(), axis.text.y = element_blank()) +
labs(x = "DIME Ideology", y = "") +
geom_text_repel(
data = subset(dt, category.slant != "other" & !(name %in% c("The Associated Press", "Associated Press", "California"))),
aes(x = cfscore, label = name),
direction = "y",
min.segment.length = 999
) +
guides(size = "none", color = "none", fill = "none")
ggsave(here("paper/figures/dime-scatter-100.png"), width = 10, height = 6)
dt %>% ggplot(aes(x = cfscore.i2, size = sqrt(n), y = n, color = cfscore.i2)) +
theme_bw() +
scale_y_log10() +
scale_x_continuous(limits = c(-1.5, 1.2)) +
scale_color_gradient(low = "blue", high = "red") +
geom_vline(xintercept = 0, lty = "dashed") +
theme(panel.grid = element_blank(), axis.text.y = element_blank()) +
labs(x = "DIME Ideology", y = "") +
geom_text_repel(
data = subset(dt, category.slant != "other" & !(name %in% c("The Associated Press", "Associated Press", "California"))),
aes(x = cfscore.i2, label = name),
direction = "y",
min.segment.length = 999
) +
guides(size = "none", color = "none", fill = "none")
ggsave(here("paper/figures/dime-scatter-100-i2.png"), width = 10, height = 6)Top DIME over time
dt7 <- dt %>% arrange(desc(n)) %>% head(7)
sources %>%
filter(org_id %in% dt7$org_id) %>%
group_by(year, organization_name, org_id, cfscore) %>%
summarize(n = n()) %>%
ggplot(aes(
x = year, y = n, color = cfscore < 0, lty = organization_name
)) +
geom_smooth(se = F) +
theme_min
Politicians
pres <- sources %>%
mutate(
pres = case_when(
str_detect(person_name, "Biden") ~ "Biden",
str_detect(person_name, "Obama") ~ "Obama",
str_detect(person_name, "Trump") ~ "Trump",
category.slant %in% c("Democrat", "Republican") ~ category.slant,
TRUE ~ NA
)
)
npy <- sources %>%
group_by(year) %>%
summarize(npy = n())
ggarrange(plotlist = list(
pres %>%
group_by(year, pres) %>%
filter(!is.na(pres)) %>%
summarize(n = n()) %>%
ggplot(aes(x = year, y = n, color = pres)) +
geom_line() +
theme_min,
# Normalize by # of sources per year...
pres %>%
group_by(year, pres) %>%
filter(!is.na(pres)) %>%
summarize(n = n()) %>%
left_join(npy) %>%
ggplot(aes(x = year, y = n / npy, color = pres, shape = pres)) +
geom_line() +
geom_point() +
scale_x_continuous(breaks = seq(2012, 2022, 4)) +
theme_min
), common.legend = T, legend = "bottom")
Journalists
Demographics
ggarrange(plotlist = list(
authors %>% ggplot(aes(x = age_est_2017)) +
geom_histogram(),
authors %>% ggplot(aes(x = elite_undergrad_ivyplus)) +
geom_bar(stat = "count"),
authors %>% ggplot(aes(x = edu.has_postgrad)) +
geom_bar(stat = "count"),
authors %>% ggplot(aes(x = field.journo)) +
geom_bar(stat = "count"),
authors %>% ggplot(aes(x = gender)) +
geom_bar(stat = "count"),
authors %>% ggplot(aes(x = race.nonwhite)) +
geom_bar(stat = "count")
))
Demographics over time
Unit of analysis: unique journalists per year
journo.years <- articles %>%
group_by(author_name, year, elite_undergrad_ivyplus, edu.undergrad, edu.has_postgrad, is_career, field.journo, age_est, gender, race.nonwhite) %>%
summarize(n = n()) %>%
filter(!is.na(author_name))
age.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(age_est > 35))) +
geom_smooth(method = "loess") +
labs(x = "Year", y = "Age > 35")
ivy.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(elite_undergrad_ivyplus))) +
geom_smooth(method = "loess") +
labs(y = "Ivy League", x = "Year")
fj.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(field.journo))) +
labs(y = "Journalism Degree", x = "Year") +
geom_smooth(method = "loess")
pg.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(edu.has_postgrad))) +
labs(y = "Postgraduate Degree", x = "Year") +
geom_smooth(method = "loess")
gender.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(gender == "female"))) +
labs(y = "Female", x = "Year") +
geom_smooth(method = "loess")
race.plt <- journo.years %>%
ggplot(aes(x = year, y = as.numeric(race.nonwhite))) +
labs(y = "Nonwhite", x = "Year") +
geom_smooth(method = "loess")
plts <- list(age.plt, ivy.plt, fj.plt, gender.plt, pg.plt, race.plt) %>%
lapply(function(p) {
p +
theme_bw() +
theme(panel.grid = element_blank()) +
scale_x_continuous(breaks = seq(2012, 2022, 2))
})
ggarrange(plotlist = plts)
ggsave(here("paper/figures/journo-agg-2.png"), width = 10, height = 6)Ideological Sources
sources %>%
group_by(year, category.slant) %>%
summarize(n = n()) %>%
ggplot(aes(x = year, y = n, color = category.slant, lty = category.slant)) +
geom_smooth(se = F) +
theme_min
sources_per_year <- sources %>%
group_by(year) %>%
summarize(year.n = n())
sources %>%
group_by(year, category.slant) %>%
summarize(n = n()) %>%
left_join(sources_per_year) %>%
ggplot(aes(x = year, y = n / year.n, color = category.slant, lty = category.slant)) +
geom_line() +
theme_min
Coverage/data quality
Articles with DIME and journalist information
articles.b <- sources %>% calculate_balance(types = c("org_category", "cfscore"))
articles.with.author <- articles.b %>% filter(!is.na(author))
articles.with.author.cfscore <- articles.with.author %>% filter(!is.na(cfscore))
nrow(articles.with.author)## [1] 12348nrow(articles.with.author.cfscore)## [1] 9915DIME coverage
nrow(sources %>% filter(!is.na(cfscore))) / nrow(sources)## [1] 0.3082604nrow(sources %>% filter(!is.na(cfscore.impute))) / nrow(sources)## [1] 0.5452656table(
!is.na(sources$cfscore),
sources$category.slant
)##
## Academic Advocacy Bureaucrat Business Democrat Environmental
## FALSE 7506 2981 9635 3647 3658 7638
## TRUE 0 2384 0 2894 7549 4265
##
## Fossil Fuel International Media Other Politician Republican
## FALSE 1180 6829 4318 3955 1578 653
## TRUE 2422 46 0 695 0 3621n_eligible <- sources %>%
filter(tolower(category.slant) %in% c("advocacy", "environmental", "fossil fuel", "business", "democrat", "republican")) %>%
nrow()
# Excludes bureaucrat, media, other
nrow(sources %>% filter(!is.na(cfscore))) / n_eligible## [1] 0.5566539nrow(sources %>% filter(!is.na(cfscore.impute))) / n_eligible## [1] 0.9846358Non policy articles cite fewer ideological sources
all.sources$cfscore_std <- all.sources$cfscore - mean(all.sources$cfscore, na.rm = T)
all.sources.balance <- all.sources %>% calculate_balance(types = c("cfscore", "org_category"))
models <-
list(
feols(n_left ~ policy_label_gpt, data = all.sources.balance),
feols(n_right ~ policy_label_gpt, data = all.sources.balance)
)
etable(models) %>% htmlTable| model 1 | model 2 | ||
|---|---|---|---|
| 1 | Dependent Var.: | n_left | n_right |
| 2 | |||
| 3 | Constant | 1.208*** (0.0117) | 0.5336*** (0.0084) |
| 4 | _______________ | _________________ | __________________ |
| 5 | S.E. type | IID | IID |
| 6 | Observations | 13,136 | 13,136 |
NYT comment counts
nyt.articles <- articles.b %>% filter(source == "New York Times")
nyt.articles %>% ggplot(aes(x = date, y = n_comments, color = cfscore)) +
geom_point(alpha = 0.3, size = 10) +
scale_color_gradient(low = "blue", high = "red")
nyt.articles %>% ggplot(aes(x = date, y = n_comments, color = balance)) +
geom_point()
hist(nyt.articles$n_comments)
sd(nyt.articles$n_comments, na.rm = T)## [1] 512.5869table(nyt.articles$n_comments %>% is.na())##
## FALSE TRUE
## 1363 3308nyt.articles %>% ggplot(aes(x = cfscore, y = n_comments)) +
geom_point() +
geom_smooth() +
theme_bw()
ggsave(here("paper/figures/nyt-comments-slant-scatter.png"), width = 6, height = 5)
summary(feols(n_comments ~ cfscore, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,193
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 371.5255 16.7083 22.23596 < 2.2e-16 ***
## cfscore 55.2263 30.4885 1.81138 0.070334 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 502.1 Adj. R2: 0.00191m <- feols(n_comments ~ elite_undergrad_ivyplus + age_est_2017 + race.nonwhite + gender + field.journo + edu.has_postgrad, data = nyt.articles)
etable(m) %>% htmlTable| m | ||
|---|---|---|
| 1 | Dependent Var.: | n_comments |
| 2 | ||
| 3 | Constant | 426.6*** (74.89) |
| 4 | elite_undergrad_ivyplusTRUE | 56.27 (36.95) |
| 5 | age_est_2017 | -0.6828 (1.708) |
| 6 | race.nonwhiteTRUE | -42.77 (53.97) |
| 7 | gendermale | -56.49. (33.13) |
| 8 | field.journoTRUE | 204.5*** (47.33) |
| 9 | edu.has_postgradTRUE | -95.68** (31.52) |
| 10 | ___________________________ | ________________ |
| 11 | S.E. type | IID |
| 12 | Observations | 1,225 |
| 13 | R2 | 0.03291 |
| 14 | Adj. R2 | 0.02815 |
What articles get more comments?
# Journalist characteristics = journalist background is sort of significant I guess?
summary(feols(log(n_comments) ~ elite_undergrad_ivyplus + age_est_2017 + race.nonwhite + gender + field.journo + edu.has_postgrad, data = nyt.articles))## OLS estimation, Dep. Var.: log(n_comments)
## Observations: 1,208
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.424881 0.196382 27.624160 < 2.2e-16 ***
## elite_undergrad_ivyplusTRUE 0.235508 0.096537 2.439571 1.4849e-02 *
## age_est_2017 -0.003774 0.004536 -0.832097 4.0552e-01
## race.nonwhiteTRUE -0.096726 0.140627 -0.687818 4.9170e-01
## gendermale -0.104422 0.086222 -1.211083 2.2610e-01
## field.journoTRUE 0.475912 0.122880 3.872993 1.1330e-04 ***
## edu.has_postgradTRUE -0.456227 0.082224 -5.548563 3.5408e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.35136 Adj. R2: 0.049822# More comments for more rightward leaning articles.. that's basically it
# Not sure exactly how to interpret this...
summary(feols(n_comments ~ balance, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,087
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 361.2239 19.9166 18.136804 < 2.2e-16 ***
## balanceTRUE 19.6879 32.5088 0.605619 0.54489
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 518.5 Adj. R2: -5.834e-4summary(feols(n_comments ~ cfscore + balance, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,085
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 386.84998 23.3908 16.538559 < 2.2e-16 ***
## cfscore 66.41133 32.5687 2.039113 0.041681 *
## balanceTRUE 3.54252 33.3777 0.106134 0.915495
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 517.9 Adj. R2: 0.002302summary(feols(log(n_comments) ~ cfscore + balance, data = nyt.articles))## OLS estimation, Dep. Var.: log(n_comments)
## Observations: 1,069
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.214308 0.062564 83.342947 < 2.2e-16 ***
## cfscore 0.253084 0.087095 2.905837 0.0037384 **
## balanceTRUE 0.020648 0.088885 0.232299 0.8163503
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.36934 Adj. R2: 0.006801# Interesting...
summary(feols(n_comments ~ cfscore + balance + n, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,085
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 209.6002 50.82554 4.123915 4.0103e-05 ***
## cfscore 65.4563 32.35542 2.023039 4.3315e-02 *
## balanceTRUE -21.7149 33.77798 -0.642871 5.2044e-01
## n 24.9750 6.36918 3.921225 9.3648e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 514.2 Adj. R2: 0.015384summary(feols(log(n_comments) ~ cfscore + balance + n, data = nyt.articles))## OLS estimation, Dep. Var.: log(n_comments)
## Observations: 1,069
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.541096 0.134595 33.738980 < 2.2e-16 ***
## cfscore 0.251914 0.085869 2.933712 3.4211e-03 **
## balanceTRUE -0.074135 0.089237 -0.830760 4.0630e-01
## n 0.094664 0.016822 5.627525 2.3364e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.34942 Adj. R2: 0.034576summary(feols(n_comments ~ cfscore + balance + post2016, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,085
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 333.33012 45.6382 7.303745 5.4209e-13 ***
## cfscore 64.74770 32.5785 1.987435 4.7126e-02 *
## balanceTRUE 6.37288 33.4287 0.190641 8.4884e-01
## post2016TRUE 60.90065 44.5990 1.365517 1.7237e-01
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 517.4 Adj. R2: 0.003098# no super intersting interaction with the post
summary(feols(n_comments ~ (cfscore > 0) * post2016, data = nyt.articles))## OLS estimation, Dep. Var.: n_comments
## Observations: 1,193
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 313.8239 42.1182 7.451035 1.7762e-13 ***
## cfscore > 0TRUE 65.1438 99.4974 0.654729 5.1277e-01
## post2016TRUE 26.7044 45.6526 0.584948 5.5869e-01
## cfscore > 0TRUE:post2016TRUE 39.8135 106.8691 0.372544 7.0955e-01
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 501.1 Adj. R2: 0.004551summary(feols(log(n_comments) ~ (cfscore > 0) * post2016, data = nyt.articles))## OLS estimation, Dep. Var.: log(n_comments)
## Observations: 1,173
## Standard-errors: IID
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.369099 0.120050 44.723830 < 2.2e-16 ***
## cfscore > 0TRUE 0.237157 0.290408 0.816632 0.4143050
## post2016TRUE -0.367322 0.129405 -2.838541 0.0046104 **
## cfscore > 0TRUE:post2016TRUE 0.102424 0.309573 0.330856 0.7408128
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.37169 Adj. R2: 0.01348nyt.articles %>% ggplot(aes(x = date, y = n_comments, color = balance)) +
geom_smooth(se = F, method = "lm") +
geom_point()
nyt.articles %>% ggplot(aes(x = date, y = n_comments, color = cfscore > 0)) +
geom_smooth(se = F, method = "lm") +
geom_point()
etable(
list(
feols(n_comments ~ elite_undergrad_ivyplus + age_est_2017 + race.nonwhite + gender + field.journo + edu.has_postgrad, data = nyt.articles),
feols(n_comments ~ cfscore + balance + n, data = nyt.articles)
)
)## model 1 model 2
## Dependent Var.: n_comments n_comments
##
## Constant 426.6*** (74.89) 209.6*** (50.83)
## elite_undergrad_ivyplusTRUE 56.27 (36.95)
## age_est_2017 -0.6828 (1.708)
## race.nonwhiteTRUE -42.77 (53.97)
## gendermale -56.49. (33.13)
## field.journoTRUE 204.5*** (47.33)
## edu.has_postgradTRUE -95.68** (31.52)
## cfscore 65.46* (32.36)
## balanceTRUE -21.71 (33.78)
## n 24.97*** (6.369)
## ___________________________ ________________ ________________
## S.E. type IID IID
## Observations 1,225 1,085
## R2 0.03291 0.01811
## Adj. R2 0.02815 0.01538
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1